{
  "best_metric": 0.6879555583000183,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.34587116299178555,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006917423259835711,
      "grad_norm": 774.7899780273438,
      "learning_rate": 5e-05,
      "loss": 134.073,
      "step": 1
    },
    {
      "epoch": 0.006917423259835711,
      "eval_loss": 8.132944107055664,
      "eval_runtime": 2.723,
      "eval_samples_per_second": 18.362,
      "eval_steps_per_second": 4.774,
      "step": 1
    },
    {
      "epoch": 0.013834846519671422,
      "grad_norm": 728.29931640625,
      "learning_rate": 0.0001,
      "loss": 132.2431,
      "step": 2
    },
    {
      "epoch": 0.020752269779507133,
      "grad_norm": 517.650146484375,
      "learning_rate": 9.990365154573717e-05,
      "loss": 91.1221,
      "step": 3
    },
    {
      "epoch": 0.027669693039342844,
      "grad_norm": 534.36181640625,
      "learning_rate": 9.961501876182148e-05,
      "loss": 39.5983,
      "step": 4
    },
    {
      "epoch": 0.03458711629917856,
      "grad_norm": 157.24337768554688,
      "learning_rate": 9.913533761814537e-05,
      "loss": 16.5417,
      "step": 5
    },
    {
      "epoch": 0.041504539559014265,
      "grad_norm": 172.1444549560547,
      "learning_rate": 9.846666218300807e-05,
      "loss": 14.6956,
      "step": 6
    },
    {
      "epoch": 0.04842196281884998,
      "grad_norm": 147.7635955810547,
      "learning_rate": 9.761185582727977e-05,
      "loss": 12.7745,
      "step": 7
    },
    {
      "epoch": 0.05533938607868569,
      "grad_norm": 48.34099578857422,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.4108,
      "step": 8
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": 83.31452178955078,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.6266,
      "step": 9
    },
    {
      "epoch": 0.06917423259835712,
      "grad_norm": 51.6795539855957,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.3071,
      "step": 10
    },
    {
      "epoch": 0.07609165585819282,
      "grad_norm": 148.9040985107422,
      "learning_rate": 9.241613255361455e-05,
      "loss": 12.422,
      "step": 11
    },
    {
      "epoch": 0.08300907911802853,
      "grad_norm": 98.24777221679688,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.296,
      "step": 12
    },
    {
      "epoch": 0.08992650237786425,
      "grad_norm": 16.14150619506836,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.996,
      "step": 13
    },
    {
      "epoch": 0.09684392563769996,
      "grad_norm": 33.403602600097656,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.1871,
      "step": 14
    },
    {
      "epoch": 0.10376134889753567,
      "grad_norm": 32.71524429321289,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.2144,
      "step": 15
    },
    {
      "epoch": 0.11067877215737137,
      "grad_norm": 32.69036865234375,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.1266,
      "step": 16
    },
    {
      "epoch": 0.11759619541720709,
      "grad_norm": 21.081871032714844,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.9504,
      "step": 17
    },
    {
      "epoch": 0.1245136186770428,
      "grad_norm": 70.64556884765625,
      "learning_rate": 7.75e-05,
      "loss": 11.4195,
      "step": 18
    },
    {
      "epoch": 0.13143104193687852,
      "grad_norm": 65.6788558959961,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.6407,
      "step": 19
    },
    {
      "epoch": 0.13834846519671423,
      "grad_norm": 47.969242095947266,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.3895,
      "step": 20
    },
    {
      "epoch": 0.14526588845654995,
      "grad_norm": 38.34162139892578,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.214,
      "step": 21
    },
    {
      "epoch": 0.15218331171638563,
      "grad_norm": 53.500396728515625,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.2879,
      "step": 22
    },
    {
      "epoch": 0.15910073497622135,
      "grad_norm": 39.04082107543945,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.329,
      "step": 23
    },
    {
      "epoch": 0.16601815823605706,
      "grad_norm": 49.369354248046875,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.3258,
      "step": 24
    },
    {
      "epoch": 0.17293558149589278,
      "grad_norm": 7.552599906921387,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.974,
      "step": 25
    },
    {
      "epoch": 0.17293558149589278,
      "eval_loss": 0.6879555583000183,
      "eval_runtime": 2.8353,
      "eval_samples_per_second": 17.635,
      "eval_steps_per_second": 4.585,
      "step": 25
    },
    {
      "epoch": 0.1798530047557285,
      "grad_norm": 25.150753021240234,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.8376,
      "step": 26
    },
    {
      "epoch": 0.1867704280155642,
      "grad_norm": 11.115327835083008,
      "learning_rate": 5.205685918464356e-05,
      "loss": 10.9443,
      "step": 27
    },
    {
      "epoch": 0.19368785127539992,
      "grad_norm": 34.211116790771484,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.3249,
      "step": 28
    },
    {
      "epoch": 0.20060527453523563,
      "grad_norm": 26.4182186126709,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.1095,
      "step": 29
    },
    {
      "epoch": 0.20752269779507135,
      "grad_norm": 26.52771759033203,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.2013,
      "step": 30
    },
    {
      "epoch": 0.21444012105490703,
      "grad_norm": 39.35798645019531,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.1891,
      "step": 31
    },
    {
      "epoch": 0.22135754431474275,
      "grad_norm": 24.50100326538086,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.1125,
      "step": 32
    },
    {
      "epoch": 0.22827496757457846,
      "grad_norm": 21.984201431274414,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.1111,
      "step": 33
    },
    {
      "epoch": 0.23519239083441418,
      "grad_norm": 38.212711334228516,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.2054,
      "step": 34
    },
    {
      "epoch": 0.2421098140942499,
      "grad_norm": 19.55695915222168,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.1752,
      "step": 35
    },
    {
      "epoch": 0.2490272373540856,
      "grad_norm": 22.37201499938965,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.0952,
      "step": 36
    },
    {
      "epoch": 0.2559446606139213,
      "grad_norm": 17.3990478515625,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.0722,
      "step": 37
    },
    {
      "epoch": 0.26286208387375704,
      "grad_norm": 20.264245986938477,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.0233,
      "step": 38
    },
    {
      "epoch": 0.2697795071335927,
      "grad_norm": 13.87209701538086,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.1106,
      "step": 39
    },
    {
      "epoch": 0.27669693039342846,
      "grad_norm": 13.097599983215332,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.0787,
      "step": 40
    },
    {
      "epoch": 0.28361435365326415,
      "grad_norm": 14.641912460327148,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.0121,
      "step": 41
    },
    {
      "epoch": 0.2905317769130999,
      "grad_norm": 13.696270942687988,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.0541,
      "step": 42
    },
    {
      "epoch": 0.2974492001729356,
      "grad_norm": 31.812328338623047,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.0109,
      "step": 43
    },
    {
      "epoch": 0.30436662343277127,
      "grad_norm": 21.586620330810547,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.0635,
      "step": 44
    },
    {
      "epoch": 0.311284046692607,
      "grad_norm": 11.610532760620117,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 10.9459,
      "step": 45
    },
    {
      "epoch": 0.3182014699524427,
      "grad_norm": 21.65961456298828,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.227,
      "step": 46
    },
    {
      "epoch": 0.32511889321227844,
      "grad_norm": 15.142019271850586,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.1067,
      "step": 47
    },
    {
      "epoch": 0.3320363164721141,
      "grad_norm": 28.59906005859375,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.1554,
      "step": 48
    },
    {
      "epoch": 0.33895373973194987,
      "grad_norm": 14.337183952331543,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 10.9071,
      "step": 49
    },
    {
      "epoch": 0.34587116299178555,
      "grad_norm": 14.704347610473633,
      "learning_rate": 1e-05,
      "loss": 10.9571,
      "step": 50
    },
    {
      "epoch": 0.34587116299178555,
      "eval_loss": 0.6945770382881165,
      "eval_runtime": 2.8248,
      "eval_samples_per_second": 17.7,
      "eval_steps_per_second": 4.602,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.658021338284032e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}